It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations
Open accessThe DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from nonstandard linguistic backgrounds (e.g., African American Vernacular English, Colloquial Singapore English, etc.).We perturb the inflectional morphology of words to craft plausible and semantically similar adversarial examples that expose these biases in popular NLP models, e.g., BERT and Transformer, and show that adversarially fine-tuning them for a single epoch significantly improves robustness without sacrificing performance on clean data. 1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · cited 2×
“Performance for this task is computed using exact match or average F1 (Rajpurkar et al., 2016).”
BackgroundMethodInfluentialConvolutional Sequence to Sequence Learning
Gehring, J., Auli, M., Grangier, D., Yarats, D., & Dauphin, Y. N. (2017) · arXiv · doi:10.48550/arxiv.1705.03122 · Cited by 2,850 · cited 1×
“We evaluate our attack on the fairseq implementation of both the Convolutional Seq2Seq (Gehring et al., 2017) and Transformer-big models, and report the BLEU score (Papineni et al., 2002) using fairseq’s implementation (Ott et al., 2019).”
MethodKnow What You Don't Know: Unanswerable Questions for SQuAD
Rajpurkar, P., Jia, R., & Liang, P. (2018) · arXiv · doi:10.48550/arxiv.1806.03822 · Cited by 2,242
Know What You Don’t Know: Unanswerable Questions for SQuAD
Rajpurkar, P., Jia, R., & Liang, P. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p18-2124 · Cited by 2,240
A Call for Clarity in Reporting BLEU Scores
Post, M. (2018) · Proceedings of the Third Conference on Machine Translation: Research Papers · doi:10.18653/v1/w18-6319 · Cited by 2,112 · cited 2×
“…perturbations are likely to be relatively natural and semantics preserving, we randomly sample 130 adversar- 6We use the sacrebleu implementation (Post, 2018). ial examples7 from each dataset and ask 3 Amazon Mechanical Turk workers to indicate (1) whether the sentences could have been written…”
MethodA Call for Clarity in Reporting BLEU Scores
Post, M. (2018) · arXiv · doi:10.48550/arxiv.1804.08771 · Cited by 2,111
Crystal, D. (2003) · doi:10.1017/cbo9780511486999 · Cited by 1,967
SpanBERT: Improving Pre-training by Representing and Predicting Spans
Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., & Levy, O. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00300 · Cited by 1,827 · cited 3×
“Following Joshi et al. (2019), we fine-tune SpanBERTSQuAD 2 for another 4 epochs on our adversarial training set.”
BackgroundMethodSpanBERT: Improving Pre-training by Representing and Predicting Spans
Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., & Levy, O. (2019) · arXiv · doi:10.48550/arxiv.1907.10529 · Cited by 1,827
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., & Kalai, A. (2016) · arXiv · doi:10.48550/arxiv.1607.06520 · Cited by 1,615 · cited 3×
“Recent research on fairness has primarily focused on racial and gender biases within distributed word representations (Bolukbasi et al., 2016), coreference resolution (Rudinger et al., 2018), sentence encoders (May et al., 2019), and language models (Bordia and Bowman, 2019).”
BackgroundAdversarial Examples for Evaluating Reading Comprehension Systems
Jia, R., & Liang, P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1215 · Cited by 1,410 · cited 1×
“Jia and Liang (2017) showed that question answering models could be misled into choosing a distractor sentence in the passage that was created by replacing key entities in the correct answer sentence.”
BackgroundchrF: character n-gram F-score for automatic MT evaluation
Popović, M. (2015) · Proceedings of the Tenth Workshop on Statistical Machine Translation · doi:10.18653/v1/w15-3049 · Cited by 1,220 · cited 2×
“We experimented with both BLEU and chrF (Popović, 2015) as our optimizing criterion6 and achieved comparable results for both, however, MORPHEUS found more adversarial examples that caused the model to output random sentences about Nicolas Sarkozy when optimizing for chrF.”
ResultCTRL: A Conditional Transformer Language Model for Controllable Generation
Keskar, N. S., McCann, B., Varshney, L. R., Xiong, C., & Socher, R. (2019) · arXiv · doi:10.48550/arxiv.1909.05858 · Cited by 751
Self-citationA critical period for second language acquisition: Evidence from 2/3 million English speakers
Hartshorne, J. K., Tenenbaum, J. B., & Pinker, S. (2018) · Cognition · doi:10.1016/j.cognition.2018.04.007 · Cited by 625 · cited 2×
“fluency test adapted from Hartshorne et al. (2018). Workers were paid a rate of at least $12/hr.”
BackgroundCase and Tense in the ‘fossilized’ steady state
Lardiere, D. (1998) · Second Language Research · doi:10.1191/026765898674105303 · Cited by 472 · cited 2×
“Since L2 (and many L1 dialect) speakers often exhibit variability in their production of inflectional morphology2 (Lardiere, 1998; Prévost and White, 2000; Haznedar, 2002; White, 2003; Seymour, 2004), we argue that NLP models should be robust to inflectional perturbations in order to minimize…”
BackgroundOn Measuring Social Biases in Sentence Encoders
May, C., Wang, A., Bordia, S., Bowman, S. R., & Rudinger, R. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1063 · Cited by 461 · cited 3×
“Recent research on fairness has primarily focused on racial and gender biases within distributed word representations (Bolukbasi et al., 2016), coreference resolution (Rudinger et al., 2018), sentence encoders (May et al., 2019), and language models (Bordia and Bowman, 2019).”
BackgroundGender Bias in Coreference Resolution
Rudinger, R., Naradowsky, J., Leonard, B., & Van Durme, B. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2002 · Cited by 443 · cited 1×
“Recent research on fairness has primarily focused on racial and gender biases within distributed word representations (Bolukbasi et al., 2016), coreference resolution (Rudinger et al., 2018), sentence encoders (May et al., 2019), and language models (Bordia and Bowman, 2019).”
BackgroundRickford, J. R., & King, S. (2016) · Language · doi:10.1353/lan.2016.0078 · Cited by 374
Gender and Dialect Bias in YouTube’s Automatic Captions
Tatman, R. (2017) · Proceedings of the First ACL Workshop on Ethics in Natural Language Processing · doi:10.18653/v1/w17-1606 · Cited by 338
The social impact of natural language processing
Hovy, D., & Spruit, S. L. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p16-2096 · Cited by 329 · cited 1×
“It is crucial that NLP systems do not amplify and entrench social biases (Hovy and Spruit, 2016).”
BackgroundIdentifying and Reducing Gender Bias in Word-Level Language Models
Bordia, S., & Bowman, S. R. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop · doi:10.18653/v1/n19-3002 · Cited by 219 · cited 2×
“, 2019), and language models (Bordia and Bowman, 2019).”
Background
Cited by
Explainable AI: a review of machine learning interpretability methods
Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S. (2020) · Entropy · doi:10.3390/e23010018 · Cited by 2,922
“In their work [164], Tan et al. proposed Morpheus, which is a method for generating textual adversarial examples by greedily perturbing the inflections of the original words in the text to find the inflected forms with the greatest loss increase, only taking into considerations the inflections that…”
Language (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050
“…(2019); Sweeney and Najafian (2019); Vaidya et al. (2019); Gaut et al. (2020); Gencoglu (2020); Hovy et al. (2020); Hutchinson et al. (2020); Kim et al. (2020); Peng et al. (2020); Rios (2020); Sap et al. (2020); Shah et al. (2020); Sheng et al. (2020); Tan et al. (2020); Zhang et al. (2020a,b).”
TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP
Morris, J., Lifland, E., Yoo, J. Y., Grigsby, J., Jin, D., & Qi, Y. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.16 · Cited by 556
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
Mehrotra, A., Zampetakis, M., Kassianik, P., Nelson, B., Anderson, H., Singer, Y., & Karbasi, A. (2023) · arXiv · doi:10.48550/arxiv.2312.02119 · Cited by 183
Measure and Improve Robustness in NLP Models: A Survey
Wang, X., Wang, H., & Yang, D. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.339 · Cited by 90
Metadata
- Authors
- Tan, S., Joty, S., Kan, M.-Y., & Socher, R.
- Venue
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Published
- 2020
- Pages
- 2920-2935
- OpenAlex
- W3023553115
- Cited by
- 84
- References
- 24
- FWCI
- 6.55
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.